© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 4272
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of countries, organizations, and cultural entities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eele
    -0.71
    conn
    -0.70
    sburg
    -0.68
    uld
    -0.66
     congr
    -0.66
     Wish
    -0.64
    sense
    -0.63
    ORK
    -0.62
     heavens
    -0.61
    edin
    -0.60
    POSITIVE LOGITS
     regarded
    1.16
     comprised
    1.16
     housed
    1.13
     headquartered
    1.12
     currently
    1.11
     considered
    1.09
     commonly
    1.09
     also
    1.08
     widely
    1.07
     located
    1.06
    Activations Density 0.358%

    No Known Activations